Neural dynamic programming based temperature optimal control for cement calcined process

Cement calcined process has large number of affected factors such as highly nonlinearity, time-lagging. There is no method to establish an accurate model of cement calcined process. In order to reduce transport energy consumption and to ensure the quality of cement clinker burning, one needs to explore different control method from the traditional PID way. Intelligent control in resolving similar issues are widely used. From the perspective of a number of balances about cement production, that is, the material balance, gas balance, heat balance. In this paper one wants to optimize cement calcined process, and to further improve the stability and efficiency. The BP network of artificial neural network is used to accomplish the control and critic modules of the algorithm. Temperatures of furnace export and kiln burning zone in cement calcined process are optimal controlled based on the fundamental principle of neural dynamic programming. The results show that, the controlled parameters tend to stability in the scope of demand, and then guarantee the quality of cement clinker calcining stability.